{"id":"W4407118209","doi":"","title":"Imagining the future of evaluation","year":2025,"lang":"en","type":"other","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"","keywords":"Geography; Computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2033926,0.001420307,0.001885531,0.00654622,0.007800883,0.02598404,0.002487262,0.01022691,0.005142823],"category_scores_gemma":[0.1533771,0.0007048892,0.001141461,0.004007245,0.07959446,0.05124135,0.0138619,0.01587223,0.001032348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02343339,"about_ca_system_score_gemma":0.02533438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005626878,"about_ca_topic_score_gemma":0.003032631,"domain_scores_codex":[0.6963693,0.272141,0.003918134,0.005080234,0.01897542,0.003515799],"domain_scores_gemma":[0.6868746,0.2787906,0.002535697,0.007521009,0.02007801,0.004200092],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000241921,0.00001634626,0.00009930192,0.0002850119,0.000007632444,0.00002442536,0.002858533,0.0002796025,0.00002302762,0.9607498,0.008809375,0.02682281],"study_design_scores_gemma":[0.00002464674,0.00004145798,0.0001413089,0.001981702,0.000009673449,0.00005722234,0.003511381,0.0008623821,0.0001271514,0.8765666,0.1166505,0.00002574892],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.003090498,0.1074018,0.03397192,0.7245491,0.003414032,0.0001123191,0.0000525052,0.0001020246,0.1273059],"genre_scores_gemma":[0.6635388,0.1342959,0.0743665,0.09258004,0.01069506,0.001435236,0.0001586023,0.0004003128,0.02252958],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.7966074,"threshold_uncertainty_score":0.9823587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04462676874332085,"score_gpt":0.3753641225315175,"score_spread":0.3307373537881966,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}